© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 72266
    Prev
    Next
    INDEX
    Explanations

    online for your favorite

    np_acts-logits-general · gemini-2.5-flash-lite

    reporting turnaround time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    0.57
    that
    0.55
    壘
    0.51
    While
    0.50
    б
    0.49
    responses
    0.47
    reactions
    0.47
    продук
    0.47
    т
    0.47
    glob
    0.47
    POSITIVE LOGITS
    MsgCallBack
    0.57
     bair
    0.48
    bandingan
    0.47
     OPERATION
    0.47
     dons
    0.47
     BER
    0.47
    baikan
    0.46
     ایر
    0.46
    orestation
    0.46
     Daerah
    0.46
    Activations Density 0.000%

    No Known Activations